Title :
A neural network for fusing the MR information into PET images to improve spatial resolution
Author :
Sase, Mikiya ; Kinoshita, Naoyuki ; Kosugi, Yukio
Author_Institution :
Interdisciplinary Graduate Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan
Abstract :
We propose a neural network architecture to fuse the anatomical information given by an MR image, into a PET image to reconstruct a reasonable activity distribution in the brain. In the network, convolutional parameters and the anatomical brain structure are expressed in pre-wired weights. When an observed PET image is given to the comparison side of the network, the activity profile of the activity layer is iteratively adjusted to constitute a reasonable model for the positron generating profile, using a modified network inversion technique
Keywords :
biomedical NMR; brain; image reconstruction; image resolution; medical image processing; neural nets; positron emission tomography; MR image; PET images; activity profile; anatomical brain structure; anatomical information; brain activity distribution; convolutional parameters; image reconstruction; iterative adjustment; network inversion technique; neural network; positron generating profile; pre-wired weights; spatial resolution; Biological neural networks; Blood flow; Deconvolution; Fuses; Image reconstruction; Image resolution; Imaging phantoms; Neural networks; Positron emission tomography; Spatial resolution;
Conference_Titel :
Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference
Conference_Location :
Austin, TX
Print_ISBN :
0-8186-6952-7
DOI :
10.1109/ICIP.1994.413714
